SnorkelRevOps pass@5
Professional Work
Published pass@5 on the 200-task SnorkelRevOps release; a correlated diagnostic of the pass@1 leaderboard.
Top models (higher is better)
| Model | Score |
|---|---|
| Grok 4.6 | 35.0 |
| Kimi K3 | 31.5 |
| Grok 4.7 | 28.1 |
| Claude Opus 5.5 | 25.8 |
| GLM-5.3 | 25.7 |
| Muse Spark 1.3 | 25.5 |
| Claude Fable 5.1 | 25.1 |
| Claude Opus 5 | 23.9 |
| GPT-6 Astra | 21.1 |
| Gemini 3.8 Flash | 14.4 |